© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 54253
    Prev
    Next
    INDEX
    Explanations

    posted on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vegano
    -0.88
     jadwal
    -0.85
    STRACT
    -0.82
     SANTOS
    -0.82
     pantolon
    -0.82
     Anglia
    -0.79
    НОЙ
    -0.78
    hadapi
    -0.78
    ELDS
    -0.77
    tanaman
    -0.77
    POSITIVE LOGITS
     Einheit
    0.88
    oole
    0.81
     Mr
    0.80
     }^{*
    0.80
     pursuit
    0.79
    ően
    0.79
     seller
    0.78
     singer
    0.76
     Y
    0.76
    Pls
    0.76
    Activations Density 0.000%

    No Known Activations